Instructions to use SystemAdmin123/SmolLM-360M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SystemAdmin123/SmolLM-360M with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="SystemAdmin123/SmolLM-360M")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("SystemAdmin123/SmolLM-360M")
model = AutoModelForCausalLM.from_pretrained("SystemAdmin123/SmolLM-360M")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use SystemAdmin123/SmolLM-360M with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SystemAdmin123/SmolLM-360M"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SystemAdmin123/SmolLM-360M",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/SystemAdmin123/SmolLM-360M

SGLang

How to use SystemAdmin123/SmolLM-360M with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "SystemAdmin123/SmolLM-360M" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SystemAdmin123/SmolLM-360M",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "SystemAdmin123/SmolLM-360M" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SystemAdmin123/SmolLM-360M",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use SystemAdmin123/SmolLM-360M with Docker Model Runner:
```
docker model run hf.co/SystemAdmin123/SmolLM-360M
```

SystemAdmin123 commited on Feb 7, 2025

Commit

84524e2

verified ·

1 Parent(s): c38e28b

End of training

Browse files

Files changed (1) hide show

README.md +15 -4

README.md CHANGED Viewed

@@ -37,7 +37,7 @@ datasets:
     system_prompt: ''
 device_map: auto
 eval_sample_packing: false
-eval_steps: 200
 flash_attention: true
 gradient_checkpointing: true
 group_by_length: true
@@ -55,11 +55,13 @@ output_dir: /root/.sn56/axolotl/tmp/SmolLM-360M
 pad_to_sequence_len: true
 resize_token_embeddings_to_32x: false
 sample_packing: true
-save_steps: 200
 save_total_limit: 1
 sequence_len: 2048
 tokenizer_type: GPT2TokenizerFast
 torch_dtype: bf16
 trust_remote_code: true
 val_set_size: 0.1
 wandb_entity: ''
@@ -78,7 +80,7 @@ warmup_ratio: 0.05
 This model is a fine-tuned version of [unsloth/SmolLM-360M](https://huggingface.co/unsloth/SmolLM-360M) on the argilla/databricks-dolly-15k-curated-en dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.0617
 ## Model description
@@ -115,7 +117,16 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
 | No log        | 0.125 | 1    | 2.5584          |
-| 2.011         | 25.0  | 200  | 2.0617          |
 ### Framework versions

     system_prompt: ''
 device_map: auto
 eval_sample_packing: false
+eval_steps: 20
 flash_attention: true
 gradient_checkpointing: true
 group_by_length: true
 pad_to_sequence_len: true
 resize_token_embeddings_to_32x: false
 sample_packing: true
+save_steps: 20
 save_total_limit: 1
 sequence_len: 2048
 tokenizer_type: GPT2TokenizerFast
 torch_dtype: bf16
+training_args_kwargs:
+  hub_private_repo: true
 trust_remote_code: true
 val_set_size: 0.1
 wandb_entity: ''
 This model is a fine-tuned version of [unsloth/SmolLM-360M](https://huggingface.co/unsloth/SmolLM-360M) on the argilla/databricks-dolly-15k-curated-en dataset.
 It achieves the following results on the evaluation set:
+- Loss: 2.0673
 ## Model description
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
 | No log        | 0.125 | 1    | 2.5584          |
+| 2.2406        | 2.5   | 20   | 2.1562          |
+| 2.136         | 5.0   | 40   | 2.0829          |
+| 2.0938        | 7.5   | 60   | 2.0711          |
+| 2.0632        | 10.0  | 80   | 2.0679          |
+| 2.0298        | 12.5  | 100  | 2.0621          |
+| 2.0168        | 15.0  | 120  | 2.0567          |
+| 2.0188        | 17.5  | 140  | 2.0686          |
+| 2.0108        | 20.0  | 160  | 2.0701          |
+| 2.0169        | 22.5  | 180  | 2.0683          |
+| 2.0109        | 25.0  | 200  | 2.0673          |
 ### Framework versions